Caveat verdict
meeting-summary
Meeting audio transcription and summarization skill using StepFun ASR; LLM calls use user-configured API keys for legitimate processing of audio recordings.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
file_read
credential_access
Findings (7)
Possible hardcoded credential
SKILL.md · code · TOKEN="$(cat ~/.huggingface_token 2>/dev/null || echo
References sudo — requests elevated privileges
references/setup-guide.md · code · sudo
pip3 install — installs Python packages at runtime
README.md · code · pip3 install
Accesses shell history/config
references/setup-guide.md · prose · downgraded · ~/.zshrc
subprocess execution — runs system commands from Python
scripts/meeting-summarize.py · prose · downgraded · subprocess.run(
Python urllib.request — network access
scripts/meeting-summarize.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
scripts/meeting-summarize.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_accessfile_read Is this flag fair?
Thanks — recorded.